Techniques for processing recorded data using docked recording devices
Inventors
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-11568233-B2
Publication Date
2023-01-31
Expiration Date
Abstract
Various embodiments of the present disclosure increase the technical utility of a recording device and local recording device system by enabling a recording device to use a machine learning model to process media content received from a separate recording device. This allows a machine learning model to be used to process media content at a local system without a remote network connection or independent of whether a remote computing system is available over a network connection. Many embodiments eliminate the need for a separate computing device altogether for purposes of using a machine learning model. Embodiments of the present disclosure also decrease the time required to complete processing of a media file by processing the media file in parallel among multiple recording devices and/or by eliminating time associated with uploading a media file to cloud-based system and receiving one or more output values back from the cloud-based system.
Core Innovation
The disclosed dock-based distributed processing system performs distributed processing of media captured by recording devices that are removably coupled to a dock. A first recording device partitions captured media content into portions, where the first portion and the second portion include separate frames of the media content, and transmits the first portion via the dock to enable other docked recording devices to process the media content in a distributed manner.
After dividing the media content, the first recording device processes the second portion using a first machine learning model, while a second recording device receives the first portion via the dock and processes the received first portion using a second machine learning model. The first machine learning model and the second machine learning model are configured to generate same values or an overlapping set of values in metadata.
The system supports local dock-based processing without relying on remote or cloud networks, and it uses parallel processing across multiple docked recording devices to reduce total processing time. Metadata generated at different recording devices is integrated into augmented media files by embedding and reconciling metadata associated with portions of media content.
Claims Coverage
The document contains three independent claims focused on dock-mediated media exchange, machine learning-based processing, and metadata generation across recording devices.
Dock-based distributed processing with media partitioning
A distributed processing system comprising a dock; a first recording device removably coupled to the dock including a first sensor, a first memory storing a first machine learning model and media content captured via the first sensor, and a first processor configured to divide the media content into a first portion and a second portion with separate frames, transmit the first portion via the dock, and responsive to dividing the media content process the second portion using the first machine learning model; and a second recording device removably coupled to the dock including a second sensor, a second memory storing a second machine learning model that generates same values or an overlapping set of values in metadata with the first machine learning model, and a second processor configured to receive the first portion via the dock and process the received first portion using the second machine learning model.
Body-worn camera metadata generation from dock-received media
A body-worn camera comprising a sensor operable to capture first media content; a memory storing a machine learning model and operable to store the first media content; and a processor configured to store the first media content in the memory, receive second media content via a dock from a second body-worn camera, process the second media content using the machine learning model to generate metadata, and transmit the metadata from the body-worn camera via the dock wherein the second media content is different from the first media content.
Body-worn camera method of processing and transmitting second metadata
A method of processing media content in a body-worn camera comprising capturing first media content with a sensor, storing the first media content in a memory, storing a machine learning model in the memory, processing the first media content using the machine learning model to generate first metadata, receiving second media content from a separate recording device, processing the second media content using the machine learning model to generate second metadata, and transmitting the second metadata to the separate recording device.
Across the independent claims, the inventive subject matter centers on dock-mediated reception and transmission of media portions or media content between recording devices, processing those portions with machine learning models, and generating and exchanging metadata produced using same or overlapping metadata values.
Stated Advantages
The system supports local dock-based processing without relying on remote or cloud networks.
Parallel processing across multiple docked recording devices reduces total processing time.
Documented Applications
Metadata generated at different recording devices is integrated into augmented media files.
Interested in licensing this patent?